Abstract
Bio-inspired tendon-driven rigid-soft coupled dexterous fingers exhibit strong nonlinearity and configuration-dependent sensitivity, making accurate modeling challenging. In discrete-time control, Jacobian-based kinematic algorithms typically rely on point-wise local linear approximations, which makes their performance sensitive to sensor sampling frequency and controller update frequency. To address this issue, we propose Jacobian Flow Matching (JFM), a structured learning framework based on Conditional Flow Matching (CFM), to learn a resolution-consistent Jacobian field that models actuation-to-motion transitions as a dynamical flow. The proposed framework supports both single-step prediction and continuous rollout via ODE integration, enabling consistent inference across temporal resolutions. Experiments on a tendon-driven rigid-soft finger show that the proposed method suppresses outlier errors and improves single-step prediction accuracy, reducing the global average RMSE by over 53% compared with a baseline discrete Jacobian learning approach. For long-horizon prediction, trajectories recovered via ODE integration achieve higher fidelity under sparse sampling (Stride = 8), reducing the RMSE median by 14.43% and the error variance by 24.87%. These results demonstrate that the learned flow-based Jacobian field provides an effective local model for offline multi-step trajectory optimization in rigid-soft coupled nonlinear systems.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Liang, T., Zeng, H., Chen, S., Zhu, Y., Lu, Z., & Luo, Z. (2026). Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger. https://omanscience.com/en/articles/learning-a-resolution-consistent-jacobian-field-for-bio-inspired-rigid-soft-finger
MLA 9
Liang, Tianyou, et al. "Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger." https://omanscience.com/en/articles/learning-a-resolution-consistent-jacobian-field-for-bio-inspired-rigid-soft-finger.
Chicago (author–date)
Liang, Tianyou, Haisen Zeng, Shanjun Chen, Yiming Zhu, Zhongyue Lu, and Zirong Luo. 2026. "Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger." https://omanscience.com/en/articles/learning-a-resolution-consistent-jacobian-field-for-bio-inspired-rigid-soft-finger.
Harvard
Liang, T., Zeng, H., Chen, S., Zhu, Y., Lu, Z. and Luo, Z. (2026) 'Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger', Available at: https://omanscience.com/en/articles/learning-a-resolution-consistent-jacobian-field-for-bio-inspired-rigid-soft-finger.
Vancouver
Liang T, Zeng H, Chen S, Zhu Y, Lu Z, Luo Z. Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger. https://omanscience.com/en/articles/learning-a-resolution-consistent-jacobian-field-for-bio-inspired-rigid-soft-finger
IEEE
T. Liang, H. Zeng, S. Chen, Y. Zhu, Z. Lu, and Z. Luo, "Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger," https://omanscience.com/en/articles/learning-a-resolution-consistent-jacobian-field-for-bio-inspired-rigid-soft-finger.